Kimi K3.1 Pro

Moonshot AIKey kimi-k3.1-proAlso reported as moonshotai/kimi-k3.1-pro, opencode-go/kimi-k3.1-pro, rmagpie/buddy/kimi-k3.1-pro, auto/kimi-k3.1-pro, opgg-ai-proxy/moonshot/kimi-k3.1-pro

Rank
#44
by active users
Active users
42
NewNew: no active users in the previous 30 days, 42 now. vs previous 30 days
Adoption
4.3%
of 966 accounts
Tokens
5.9B
cache included
Est. cost
$1.3K
at public list prices
First seen
Oct 16, 2026
in any submission

Oct 15 – Nov 13, 2026 (UTC)966 accounts100% of tokens from an identified modelData through Nov 13, 2026, 05:14 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

2 active users on Nov 13, 2026

Daily active users for Kimi K3.1 Pro, Oct 15, 2026 to Nov 13, 2026. Peak 9. Use the left and right arrow keys to read each day.1050
Show daily values
Daily active users and tokens for Kimi K3.1 Pro
Date (UTC)Active usersTokens
Oct 15, 202600
Oct 16, 2026115M
Oct 17, 202600
Oct 18, 202600
Oct 19, 202600
Oct 20, 202600
Oct 21, 202600
Oct 22, 202600
Oct 23, 202600
Oct 24, 2026686.6M
Oct 25, 202621.1B
Oct 26, 2026928.9M
Oct 27, 2026672.1M
Oct 28, 20267359M
Oct 29, 2026444.1M
Oct 30, 20264293.4M
Oct 31, 20266222.3M
Nov 1, 20267306.9M
Nov 2, 20268125.9M
Nov 3, 2026654.1M
Nov 4, 20266220.4M
Nov 5, 20263134.5M
Nov 6, 20267498.9M
Nov 7, 20267107.7M
Nov 8, 2026521.1M
Nov 9, 2026573.2M
Nov 10, 2026375.4M
Nov 11, 2026223.7M
Nov 12, 202631.4B
Nov 13, 20262615.3M

Token mix

How the 5.9B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input3.6%
  • Output0.2%
  • Cache read96%
  • Cache write<0.1%
  • Reasoning<0.1%

Agents that carry Kimi K3.1 Pro

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. OpenCode40% of this model's tokens11active users
  2. Pi40% of this model's tokens6active users
  3. Claude Code7.4% of this model's tokens5active users
  4. Kimi6.3% of this model's tokens1active users
  5. WorkBuddy2.3% of this model's tokens6active users
  6. Hermes Agent2.2% of this model's tokens3active users
  7. Oh My Pi0.9% of this model's tokens3active users
  8. CodeBuddy0.6% of this model's tokens3active users
  9. Senpi (OmO Native)0.5% of this model's tokens3active users
  10. DeepSeek Harness0.2% of this model's tokens3active users
  11. Codex CLI<0.1% of this model's tokens1active users
  12. cc-mirror/curl<0.1% of this model's tokens1active users
  13. cc-mirror/mozilla<0.1% of this model's tokens1active users

Benchmarks

The best result for Kimi K3.1 Pro in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    161.4
    Rank #16 of 158 matched modelsNo conditions reportedModel released Oct 23, 2026Source: epoch.ai (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    94.2%
    Rank #12 of 160 matched modelsMaxRun date Nov 6, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.5%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    78.2%
    Rank #23 of 90 matched modelsMaxRun date Nov 6, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 95.1%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    62.2%
    Rank #17 of 86 matched modelsMaxRun date Nov 6, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.1, CursorBench, DeepSWE, FrontierSWE, Agent Arena, WebDev Arena. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. Moonshot AI is the lab's own API and the reference price for the estimates below.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.29
Est. per 1M tokens
96% cache reads
At the community mix
$0.30
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$4
Per 1M tokens at list prices
No cache

Cache reads were 96% of Kimi K3.1 Pro tokens in the last 30 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • Moonshot AI list prices per 1M tokens: input $2, output $10, cache read $0.20, cache write $2.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.

List prices by provider

  • Moonshot AIReferencekimi-k3.1-pro
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2 cache write per 1M tokens1.05M tokens of context
  • Amazon Bedrockus.moonshotai.kimi-k3.1
    $4.40 input per 1M tokens$22 output per 1M tokens$0.22 cache read per 1M tokens$5.50 cache write per 1M tokens1.05M tokens of context
  • OpenRoutermoonshotai/kimi-k3.1-pro
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewaymoonshotai/kimi-k3.1-pro
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokensCache write not listed1M tokens of context
Show 4 more providersShow fewer providers
  • Together AImoonshotai/Kimi-K3.1-Pro
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Fireworks AIaccounts/fireworks/models/kimi-k3p1-pro
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Deep Inframoonshotai/Kimi-K3.1-Pro
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Basetenmoonshotai/Kimi-K3.1-Pro
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokensCache write not listed1M tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
1.05M tokens
Max output
1.05M tokens
Input
Text, Image, Video
Output
Text
Knowledge cutoff
— not listed
Release date
Oct 23, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Kimi K3.1 Pro most in this period, by tokens. Hidden accounts are never listed.

  1. 1Woonggi Min@minpeter2Btokens—est. cost2active daysno price · 2 active days
  2. 2luke eldridge@lkeld1.1Btokens$260est. cost2active days$260 est. cost · 2 active days
  3. 3Andrei Branga@andreibranga676.8Mtokens$212est. cost10active days$212 est. cost · 10 active days
  4. 4Abhishek gahlot@abhishekgahlot2421.5Mtokens$393est. cost4active days$393 est. cost · 4 active days
  5. 5Christopher Butler@techsaint406.2Mtokens$169est. cost18active days$169 est. cost · 18 active days
  6. 6大鹏@KongValley396.2Mtokens—est. cost2active daysno price · 2 active days
  7. 7Soju06@Soju06371.5Mtokens$111est. cost7active days$111 est. cost · 7 active days
  8. 8vipox233@vipox233103.2Mtokens$28est. cost3active days$28 est. cost · 3 active days
  9. 9Kabir Acharya@KabirAcharya84.8Mtokens$27est. cost2active days$27 est. cost · 2 active days
  10. 10Zenco@notzenco83.5Mtokens$24est. cost1active days$24 est. cost · 1 active days

More from Moonshot AI

Other Moonshot AI models in the same period, by active users.

  1. Kimi K35.9% adoption57active users
  2. Kimi K2.7 Code1.8% adoption17active users
  3. Kimi For Coding1.3% adoption13active users
  4. Kimi K3 10.7% adoption7active users
  5. Kimi K3 Max0.4% adoption4active users
  6. Kimi For Coding Highspeed0.4% adoption4active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • Epoch AIEpoch Capabilities Index, Epoch's own runs and the external results it collects.CC BY 4.0 · Retrieved Nov 12, 2026 · Data through Nov 9, 2026Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.
  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count